open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-05-02 17:45:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1337 commits 21 branches 5 tags 37 MiB
Commit graph

10 commits

Author SHA1 Message Date
Zafir Stojanovski
49b1dbbcce
Fix misleading instruction in shortest_path asking for "length" instead of path (#523) 
The prompt asked to "find the length of the shortest path" but the expected
answer is a sequence of directions. This caused models to answer with a number
instead of directions, degrading evaluation results.

Closes #522

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-25 13:02:23 +01:00
Zafir Stojanovski
c6663cdb81
fix(training): Prepend <think> token in format reward (#396) 
* prepend think token in format reward

* pre commit + fix some default vals

* add checkpoint config
 2025-03-28 09:45:17 +01:00
Andreas Koepf
2802066233 remove data/ from main .gitignore 2025-03-07 16:16:40 +01:00
Zafir Stojanovski
5109ed89c9 pre-commit 2025-02-23 13:11:31 +01:00
Zafir Stojanovski
6bbec2ac4e exploratory notebook 2025-02-22 00:46:33 +01:00
tohskai
847442ef0a
Add PolynomialMultiplicationDataset (#64) 
* Add PolynomialMultiplicationDataset
 2025-02-07 14:06:41 +01:00
abdulhakeem
715102c277 Remove .DS_Store 2025-02-01 20:39:37 -06:00
Rich Jones
99bf648989 initial bf working, contrib not committed 2025-01-30 15:38:03 +01:00
Andreas Koepf (aider)
3f80fd7b80 build: Initialize reasoning_gym package structure with packaging and development setup 2025-01-23 10:50:54 +01:00
Andreas Koepf
530cb523c8 chore: Add .gitignore with .aider and .env files 2025-01-23 10:50:53 +01:00